We compare a variety of different anatomic connectivity measures, including several novel ones, that may help in distinguishing Alzheimer's disease (AD) patients from controls. We studied diffusion-weighted magnetic resonance imaging from 200 subjects scanned as part of the Alzheimer's Disease Neuroimaging Initiative. We first evaluated measures derived from connectivity matrices based on whole-brain tractography; next, we studied additional network measures based on a novel flow-based measure of brain connectivity, computed on a dense 3-dimensional lattice. Based on these 2 kinds of connectivity matrices, we computed a variety of network measures. We evaluated the measures' ability to discriminate disease with a repeated, stratified 10-fold cross-validated classifier, using support vector machines, a supervised learning algorithm. We tested the relative importance of different combinations of features based on the accuracy, sensitivity, specificity, and feature ranking of the classification of 200 people into normal healthy controls and people with early or late mild cognitive impairment or AD.
Current approaches used to classify Alzheimer's disease (AD) (Klöppel et al., 2008 and Kohannim et al., 2010) rely on features such as volumetric measures from anatomic regions in magnetic resonance imaging (MRI) of the brain, cerebrospinal fluid biomarkers, apolipoprotein E genotype, age, sex, body mass index, and, in some cases, clinical and cognitive tests. Here, we attempted to improve our understanding of the best features for AD classification by studying the utility of a variety of brain connectivity measures derived from diffusion-weighted images (DWIs) of the brain. Some of the features we chose came from standard tractography-based maps of fiber connectivity (Rubinov and Sporns, 2010) between brain regions; we supplemented these with more novel features derived from a flow-based connectivity method (Prasad et al., 2013b). We aimed to understand the information contained in the raw connectivity matrices versus network measures derived from them; we used all the resulting features to differentiate diagnostic categories related to AD (e.g., mild cognitive impairment [MCI]). To do this, we employed support vector machines (SVMs), a machine learning algorithm for classification, to learn from training data and then classify a separate test set.
Cui et al. (2012) used SVMs to classify amnestic MCI based on features indexing anatomic atrophy through segmentations of T1-weighted MRI and fraction anisotropy values from diffusion images using tract-based spatial statistics. They ranked the features using Fisher scores and selected the best-performing subset using cross-validation. They achieved an accuracy of 71.09%, sensitivity of 51.96%, and specificity of 78.40% for the classification of amnestic MCI. Our method differs in that we use only measures of connectivity from diffusion images for our feature set, and the ranking is computed within a set of features we are interested in evaluating. Laplacian regularized least squares was used to classify AD in Zhang and Shen (2011) where they tried to incorporate structural MRI, PET imaging data, and cerebrospinal fluid biomarker features from MCI into an AD classifier, which achieved a performance of almost 95% accuracy. In our case, we explore classification of both MCI and AD and focus on the information contained in different types of connectivity features. Cortical thickness features from structural MRI were evaluated by Eskildsen et al. (2012) using classification although they focused on conversion from MCI to AD and achieved accuracies ranging from 70% to 76% depending on the time to conversion, in contrast we used classification as a means to understand the information captured in measures of connectivity. The emphasis in the present study is to explore and understand which diffusion-based network measures are predictive of AD in contrast to the goal of optimizing the accuracy of classification in previous studies.
Our results and experiments seek to characterize the information contained in different features used to represent connectivity in the brain. This is related to the problem of feature selection methods (Guyon and Elisseeff, 2003), which rank features in a meaningful way to understand the ones that are important and those that can be discarded because they are redundant or irrelevant. One approach to select the best features (Peng et al., 2005) is to use mutual information to find the most relevant features for a target class. Another popular approach is the least absolute shrinkage and selection operator (Tibshirani, 1996) that uses a linear model and its regression coefficients to choose the best subset of features. De Martino et al. (2008) chose the most informative voxels in functional MR images using a recursive feature elimination approach that repeatedly trains an SVM model to remove features contributing a small amount to the training model. In our technique, we use the accuracy from classification to evaluate different types of brain connectivity features and to understand which ones may have an advantage to classifying MCI or AD. In addition, we used the SVMs to rank the features within the different feature sets to get a better description of what features were driving the classifier.
Our connectivity measure computation, classification framework, and ranking were applied to publicly available structural and diffusion MRI from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (Mueller et al., 2005). We studied neuroimaging data from 200 subjects: 50 normal healthy controls, 38 people with late MCI (LMCI), 74 with early MCI (EMCI), and 38 AD patients.
We extracted measures of connectivity between 68 automatically parcellated regions of interest on the cortex using both fiber and flow connectivity methods and organized the information into connectivity matrices. From these connectivity matrices, we computed a variety of widely used network measures. These features were then fed into a repeated, stratified 10-fold cross-validation design, using SVMs to classify controls versus AD, controls versus EMCI, controls versus LMCI, and EMCI versus LMCI. Our results show a significant difference in the accuracy of various combinations of features that were used to distinguish between the various diagnostic groups.
